© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14308
    Prev
    Next
    INDEX
    Explanations

    phrases related to computer system management, specifically user authentication and security measures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    678
    +0.10
    0.3%
    1870
    +0.10
    0.3%
    919
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    383
    +0.10
    0.04
    919
    +0.10
    0.02
    1340
    +0.08
    0.05
    Negative Logits
     apprehen
    -1.12
     intersper
    -1.11
     withal
    -1.09
     quitted
    -1.08
     gaily
    -1.08
     unspeak
    -1.05
     reluct
    -1.03
     indescri
    -1.02
     vainly
    -1.02
     cushi
    -1.01
    POSITIVE LOGITS
     section
    0.90
     portion
    0.82
     category
    0.77
     segment
    0.76
     aspect
    0.74
     option
    0.73
     component
    0.70
     module
    0.67
    Obrigada
    0.66
    Dimensiones
    0.65
    Activations Density 0.421%

    No Known Activations